Cluster Touch: Improving Touch Accuracy on Smartphones for People with Motor and Situational Impairments

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems Pub Date : 2019-05-02 DOI:10.1145/3290605.3300257

Martez E. Mott, J. Wobbrock

{"title":"Cluster Touch: Improving Touch Accuracy on Smartphones for People with Motor and Situational Impairments","authors":"Martez E. Mott, J. Wobbrock","doi":"10.1145/3290605.3300257","DOIUrl":null,"url":null,"abstract":"We present Cluster Touch, a combined user-independent and user-specific touch offset model that improves the accuracy of touch input on smartphones for people with motor impairments, and for people experiencing situational impairments while walking. Cluster Touch combines touch examples from multiple users to create a shared user-independent touch model, which is then updated with touch examples provided by an individual user to make it user-specific. Owing to this combination, Cluster Touch allows people to quickly improve the accuracy of their smartphones by providing only 20 touch examples. In a user study with 12 people with motor impairments and 12 people without motor impairments, but who were walking, Cluster Touch improved touch accuracy by 14.65% for the former group and 6.81% for the latter group over the native touch sensor. Furthermore, in an offline analysis of existing mobile interfaces, Cluster Touch improved touch accuracy by 8.21% and 4.84% over the native touch sensor for the two user groups, respectively.","PeriodicalId":20454,"journal":{"name":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"26","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3290605.3300257","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 26

Abstract

We present Cluster Touch, a combined user-independent and user-specific touch offset model that improves the accuracy of touch input on smartphones for people with motor impairments, and for people experiencing situational impairments while walking. Cluster Touch combines touch examples from multiple users to create a shared user-independent touch model, which is then updated with touch examples provided by an individual user to make it user-specific. Owing to this combination, Cluster Touch allows people to quickly improve the accuracy of their smartphones by providing only 20 touch examples. In a user study with 12 people with motor impairments and 12 people without motor impairments, but who were walking, Cluster Touch improved touch accuracy by 14.65% for the former group and 6.81% for the latter group over the native touch sensor. Furthermore, in an offline analysis of existing mobile interfaces, Cluster Touch improved touch accuracy by 8.21% and 4.84% over the native touch sensor for the two user groups, respectively.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

集群触摸:为有运动和情境障碍的人提高智能手机上的触摸准确性

我们提出了Cluster Touch，这是一个结合了用户独立和用户特定的触摸偏移模型，可以提高智能手机上运动障碍患者和行走时遇到情境障碍的人的触摸输入的准确性。Cluster Touch结合来自多个用户的触摸示例来创建一个共享的用户独立触摸模型，然后使用单个用户提供的触摸示例来更新该模型，使其具有用户特异性。由于这种组合，Cluster Touch允许人们通过提供仅20个触摸示例来快速提高智能手机的准确性。在一项有12名运动障碍患者和12名无运动障碍患者的用户研究中，与原生触摸传感器相比，Cluster Touch将前者的触摸精度提高了14.65%，后者提高了6.81%。此外，在对现有移动界面的离线分析中，对于两个用户群体，Cluster Touch的触摸精度分别比原生触摸传感器提高了8.21%和4.84%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

自引率

0.00%

发文量

期刊最新文献

HAExplorer Influencers in Multiplayer Online Shooters: Evidence of Social Contagion in Playtime and Social Play SeeingVR Trigger-Action Programming for Personalising Humanoid Robot Behaviour "Pretty Close to a Must-Have": Balancing Usability Desire and Security Concern in Biometric Adoption